medigraphic.com
ISSN 1527-3172 (Electronic)

2017, Number 2-3

<< Back Next >>

MEDICC Review 2017; 19 (2-3)

Statistical modeling in health research: Purpose drives approach

González-Ferrer V, González-Ferrer Y, Ramírez-Marino M

Language: English
References: 30
Page: 71-74
PDF size: 133.94 Kb.


ABSTRACT

Statistical modeling is commonly used in both predictive and explanatory studies in health research. Its use in Cuba continues to grow, although it is sometimes employed inappropriately, which can lead to errors that imperil validity. This article attempts to shed light on faulty practices in statistical modeling by examining and discussing the main differences between explanatory and predictive models, with reference to the following: study objectives, theoretical considerations in model-building, aspects requiring assessment, variable and algorithm selection, analysis of confounders, treatment of multicollinearity, and reporting results.


REFERENCES

  1. Hernán MA, Robins JM. Instruments for causal inference: an epidemiologist´s dream? Epidemiol. 2006 Jul;17(4):360–72.

  2. Rencher AC, Schaalje GB. Linear Models in Statistics. 2nd ed. New Jersey: John Wiley-Interscience; 2008 Jan 2. 688 p.

  3. Lindsey JK. Nonlinear Models for Medical Statistics. Oxford (UK): Oxford University Press; 2001 Sep 20. 296 p.

  4. Domínguez González EJ, Piña Prieto LR, Cisneros Domínguez CM, Romero García LI. Escala predictiva de mortalidad en la oclusión intestinal mecánica. Rev Cubana Cir. 2015 Apr– Jun;54(2):129–39. Spanish.

  5. García Mederos Y, Zamora Matamoros L, Sagaró del Campo N. Análisis estadístico implicativo en la identifi cación de factores de riesgo en pacientes con cáncer de pulmón. MEDISAN. 2015 Aug;19(8):944–54. Spanish.

  6. Bayarre H. Prevalencia y factores de riesgo de discapacidad en ancianos. Ciudad de La Habana y Las Tunas, 2000 [thesis] [Internet]. [Havana]: National School of Public Health (CU); 2003 [cited 2016 Apr 12]. 141 p. Available from: http://tesis.repo.sld.cu/70/1/Bayarre.pdf. Spanish.

  7. Fuentes Díaz Z. Modelos multidimensionales pronósticos de mortalidad quirúrgica en intervenciones electivas no cardiacas [thesis] [Internet]. [Camagüey]: University of Medical Sciences of Camagüey; 2014 [cited 2016 Apr 12]. 131 p. Available from: http://tesis.repo.sld.cu/866/1/ Zaily_Fuentes_D%C3%ADaz.pdf. Spanish.

  8. Betancourt Cervantes JR. Nuevo índice predictivo para relaparotomías [thesis] [Internet]. [Havana]: Military Medicine Higher Institute of Havana; 2008 [cited 2016 Apr 24]. 87 p. Available from: http://tesis.repo.sld.cu/173/1/Betancourt_Julio .pdf. Spanish.

  9. Jiménez Guerra SD. Modelo predictivo de neumonía y mortalidad en pacientes ventilados [thesis] [Internet]. [Matanzas (CU)]: Military Medicine Higher Intstitute of Matanzas (CU); 2008 [cited 2016 Jul 9]. 201 p. Available from: http://tesis .repo.sld.cu/204/1/Jiménez_Guerra.pdf. Spanish.

  10. Shmueli G. To explain or to predict? Statistical Science. 2010;25(2):289–310.

  11. Gupta M, Moily NS, Kaur H, Jajodia A, Jain S, Kukreti R. Identifying a predictive model for response to atypical antipsychotic monotherapy treatment in south Indian schizophrenia patients. Genomics [Internet]. 2013 Aug [cited 2015 Oct 2];102(2):131–5. Available from: https://linking hub.elsevier.com/retrieve/pii/S0888-7543 (13)00018-9

  12. Direkvand-Moghadam A, Khosravi A, Sayehmiri K. Predictive factors for preeclampsia in pregnant women: a receiver operation character approach. Arch Med Sci. 2013 Aug 30;9(4):684–9.

  13. Billings J, Blunt I, Steventon A, Georghiou T, Lewis G, Bardsley M. Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (PARR-30). BMJ Open [Internet]. 2012 Aug 10 [cited 2015 Oct 2];2(4). pii: e001667. DOI: 10.1136/bmjo pen-2012-001667. Available from: http://bmjo pen.bmj.com/content/2/4/e001667.full

  14. Lang H. Elements of regression analysis. Stockholm: KTH Mathematics; 2016 Jul. 58 p.

  15. Berlanga-Silvente V, Vilà-Baños R. Cómo obtener un modelo de regresión logística binaria con SPSS. REIRE [Internet]. 2014 [cited 2017 May 15];7(2):105–18 . Available from: http://www .ub.edu/ice/reire.htm. Spanish.

  16. Gispert Abreu EA. Morbilidad por caries dental y probabilidad de agravamiento en niños de 6 a 11 años [thesis] [Internet]. [Havana]: Higher Institute of Medical Sciences of Havana, School of Dentistry; 2007. [cited 2016 Jul 9]. 187 p. Available from: http://tesis.repo.sld.cu/236/1/ Gispert_Abreu.pdf. Spanish.

  17. León Sánchez MA, Linares Guerra EM. La regresión logística binaria como instrumento para la predicción de deterioro inmunológico a partir de indicadores nutricionales en personas con VIH/SIDA. Rev Invest Operacional. 2014;35(1):35–48. Spanish.

  18. Moons KG, Royston P, Vergouwe Y, Grobbee DE, Altman DG. Prognosis and prognostic research: what, why, and how? BMJ. 2009 Feb 23;338:b375. DOI: 10.1136/bmj.b375.

  19. Rothman KJ, Greenland S, Lash TL. Modern Epidemiology. 3rd ed. New York: Lippincott, Williams & Wilkins; 2009 Mar 1.

  20. Fewell Z, Davey Smith G, Sterne JA. The impact of residual and unmeasured confounding in epidemiologic studies: A simulation Study. Am J Epidemiol. 2007 Sep 15;166(6):646–55.

  21. Hernán MA. A defi nition of causal effect for epidemiological research. J Epidemiol Community Health. 2004 Apr;58(4):265–71.

  22. González Sanz ÁM, González Nieto BA, González Nieto E. Salud dental: relación entre la caries dental y el consumo de alimentos. Nutr Hosp [Internet]. 2013 Jul [cited 2015 Oct 2];28(Suppl 4):64–71. Available from: http:// scielo.isciii.es/scielo.php?script=sci_arttext&pid =S0212-16112013001000008. Spanish.

  23. Calderón Saldaña JP, Alzamora de los Godos Urcia L. Regresión logística aplicada a la epidemiología. Rev Salud Sexualidad Soc. 2009;1(4). Spanish.

  24. Bacallao J. Mediating variable. In: Sarah Boslaugh, editor. Encyclopedia of Epidemiology. Vol. 2. New York: Sage; 2007:656–7.

  25. Steyerberg EW, Moons KGM, van der Windt DA, Hayden JA, Perel P, Schroter S, et al. Prognosis research strategy (PROGRESS) 3: prognostic model research. PLoS Med. 2013;10(2):e1001381. DOI: 10.1371/journal. pmed.1001381.

  26. Hosmer DW, Lemeshow S. Applied Logistic Regression. 2nd ed. New York: Wiley & Sons; 2000 Sep 15. 392 p.

  27. Gonçalves L, Subtil A, Oliveira MR, de Zea Bermudez P. ROC curve estimation: an overview. REVSTAT [Internet]. 2014 Mar [cited 2017 May 17];12(1):1–20. Available from: https://www.ine .pt/revstat/pdf/rs140101.pdf

  28. Nagelkerke NJD. A note on a general defi nition of the coeffi cient of determination. Biometrika.1991 Sep;78(3):691–2.

  29. Velicer WF, Jackson DN. Component analysis versus common factor analysis-some further observation. Multivariate Behav Res. 1990 Jan1;25(1):97–114.

  30. Hospital Universitario Ramón y Cajal [Internet]. Madrid: Hospital Universitario Ramón y Cajal; c2017. Material docente de la Unidad de Bioestadística Clínica. El problema de la colinealidad; 2010 [cited 2015 Mar 4]. Available from: http://www.hrc.es/bioest/Reglin_15.html. Spanish.




2020     |     www.medigraphic.com